Quantum-inspired Neural Network Based on Stochastic Liouville-von Neumann Equation for Sentiment Classification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A7K62P27L" target="_blank" >RIV/00216208:11320/25:7K62P27L - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205003619&doi=10.1109%2fIJCNN60899.2024.10650170&partnerID=40&md5=9ce37a939da1c173422d593ac10513d3" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205003619&doi=10.1109%2fIJCNN60899.2024.10650170&partnerID=40&md5=9ce37a939da1c173422d593ac10513d3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN60899.2024.10650170" target="_blank" >10.1109/IJCNN60899.2024.10650170</a>

Result language

angličtina

Original language name

Quantum-inspired Neural Network Based on Stochastic Liouville-von Neumann Equation for Sentiment Classification

Original language description

Quantum-inspired models have shown enhanced capabilities in various language tasks, including question answering and sentiment analysis. However, current complex-valued-based models primarily focus on sentence embedding, overlooking the significance of the quantum evolution process and the extra time cost incurred by complex expressions. In this work, we present a novel quantum-inspired neural network, SSS-QNN, which integrates the Stochastic Liouville-von Neumann Equation (SLE) to simulate the evolution process and the complex-valued simple recurrent unit (SRU) to reduce the time cost, offering the model physical meaning, thus enhancing the interpretability. We conduct comprehensive experiments on both sentence-level and document-level sentiment classification datasets. Compared to traditional models, large language models, and quantum-inspired models, SSS-QNN demonstrates competitive performance in accuracy and time cost. Additional ablation tests verify the effectiveness of the proposed modules. © 2024 IEEE.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proc Int Jt Conf Neural Networks

ISBN

979-835035931-2

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

1-8

Publisher name

Institute of Electrical and Electronics Engineers Inc.

Place of publication

—

Event location

Yokohama

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—